Plugins

Model sampling sliders (temperature / maxTokens) in the composer: override every model request for all providers via the agent/request hook, with hot/persist modes.

Right-hand widget rail for the DSH Web UI: live session stats (turns, LLM/tool time, TTFT, speed, cache, tokens) and OpenCode Go quota via a same-origin host proxy; extensible widget registry for more platform usage widgets, visuals, utility actions and external integrations.

A DeepSeek Harness plugin for real-time token tracking and highly accurate session cost estimation, featuring dynamic peak/off-peak pricing support.

Activity heatmap in the DSH Web sidebar: GitHub-style grid of daily commits, token usage, and estimated spend, with a today stats line for all-session token totals, cache hit rate, and per-model auto-priced cost.

Draggable grid-aligned workbench of 28 mini-cards in the margins of the conversation (API balance, token usage, cost, context pressure, todos, goal, usage heatmap, GitHub repo, image relay), with S/M/L/XL size tiers.

DeepSeek API balance and 24-hour usage dashboard in Settings, with estimated spend, token counts, request counts, and an hourly timeline.

Bring WorkBuddy, Qoder and Trae subscription models into DeepSeek Harness with multi-account failover, per-account HTTP(S) proxies and model visibility controls. Sign-in and chat calls go through the community opencode-*-auth adapter packages (installed with the plugin at pinned versions) to each vendor's China-region service; accounts and tokens are kept in DSH's credential store, and a free-models-only filter is on by default.

A DSH context-compaction plugin: when the route supports images, it renders the middle of a session history into locally generated 1-bit bitmap frames for the vision model, while the exact head and tail, a bounded exact-token index and a FILES index stay as text.

Tsinghua MadModel provider for DSH: renews the campus token automatically, switches between campus direct access and WebVPN, and serves model requests through a loopback transport with per-model queuing.

GitHub-style activity heatmap in the sidebar, one cell per day over 30/90/365-day ranges, with token usage and estimated cost per model and editable per-model prices.

Kifu-style context compression for long DSH sessions: each step folds new turns into a DAG (node = position, edge = attempted fix), injects only a ~417-token hot list (2000-edge fixture, L5 tier), and adds failure memory plus position-repetition detection. Each span is summarized exactly once, so what is retained does not decay with the number of compactions.

A biomimetic memory plugin for DSH that folds context into token clues and reconstructs memories on-demand.

Android in the sidebar, driven by text instead of screenshots. 30 tools read the real UI tree, tap by text/id/ref, measure animation motion, and mirror the screen into the sidebar where you circle a spot and send it back with one sentence — the host ships the marked-up frame plus the controls inside the circle to the chat. Token cost is the point: a screen check is a 200-600 token text block, not a 1k+ token screenshot, and a warm check costs 100-200 ms of wall clock. Video is raw H.264 straight into WebCodecs — no transcoding — with p50 2 ms host-write to decoded frame over a 26 s run, one decoder, zero dropped frames; it falls back to MSE on its own and ?avc=0 forces the old path. Sound is one switch, off by default and remembered per serial, so the default path pays nothing; when on, audio rides its own socket (48 kHz stereo PCM, measured 22 s / 1047 packets / 0 loss) and closing the window reclaims it too. Nothing runs behind your back: closing the window stops capture at once, the viewer-less host decoder, recorder and device-side server are gone within 3 s, an idle channel is dropped after 90 s, and a request you closed is never reopened by itself. `adb_proc audit` settles who leaked what in one call. Bundled helpers, no extra services; needs adb and ffmpeg on the host, and the adb_ocr tool plus the OCR fallback for empty UI trees are macOS-only.

Windows-only model provider for Google Antigravity CLI, continuing Darkings/dsh-agy-provider (install as dsh-agy-cli; do not install alongside the original). It reads the Antigravity token from the Windows Credential Manager and sends it only to the Google Cloud Code endpoints, lets DSH own the harness tool policy, streams the tail without rollback, and tracks the real quota windows.

Replaces the DSH Web connection provider to skip BrowserAuth entirely so the Web UI opens directly without pasting the random startup token, gated to nine verified DSH version pairs with strict host/client matching that sleeps automatically on unknown or mixed versions, and reverts fully on uninstall; web profiles only.

Usage statistics: a usage and reference-cost panel for DeepSeek Harness with today, 7-day, 30-day, all-time and custom ranges aggregated by hour or day; a model filter and a per-model breakdown of requests, input and output tokens, cache, reference cost and share; a model-share card showing the top four models by total tokens with the rest grouped as others; a reference price list generated from opencode Zen and DeepSeek's published rates, with DeepSeek models billed by Beijing weekday peak/off-peak windows and Chinese public holidays; a pricing-match dialog to point an unmatched model at a reference model or type per-million rates by hand; reference cost switchable between ¥ and $ at a fixed 1 USD = 7 CNY; and a yearly heatmap drawn only with theme variables, with no third-party chart library.

Finishes 头歌 (EduCoder) homework over the platform JSON API, with no browser automation. educoder_sweep scans every course for homeworks that still have unfinished challenges — complete homeworks are skipped without reading a single challenge, so a full-account scan costs no model tokens — and can finish them; multiple-choice challenges also cost no model tokens, because the platform returns the answer key in any submission response, while code challenges are generated by the model, uploaded with evaluate:0 and graded once per challenge, then retried using the error report the platform returns. Three tools: educoder_sweep, educoder_homework, educoder_account.

Injects a small continuity pointer at the start of a new session, naming the previous session and any handoff file, and reuses DSH's own compaction summary when there is no handoff file.

Three switchable low-glare themes (Warm Paper, Sage Green, Warm Grey) for the DeepSeek Harness GUI, each a full alias-token layer with a light and a dark face.

Exposes the models already configured in DeepSeek Harness through an OpenAI-compatible gateway, so other local projects can call them with any standard OpenAI client. Multiple provider candidates share one named group with ordered, balanced or random dispatch; upstream failures before any output switch to the next candidate transparently, and rate-limited requests are retried after the provider's backoff. Per-candidate call statistics (attempts, answers, failures, token/TTFT totals) appear as badges in the settings page, and daily aggregates persist to a local file with a 30-day heatmap and trend view. Until you create a key in the UI, the endpoint accepts calls from anyone who can reach it; keys (stored as SHA-256 hashes) then turn authentication on, and the endpoint stays locked even after the last key is revoked. Exposing the optional LAN listener without a key leaves the port open to the whole network. Runs on DSH 0.1.2-rc.1 through 0.1.7-alpha.1 and later.

Universal Model Context Protocol (MCP) bridge for DeepSeek Harness: connects agents to stdio/sse/websocket MCP servers with a 10k dormant scale engine, sub-millisecond BM25 tool search, dynamic token budgeting, and a real-time web UI dashboard.

Session usage dashboard: day/hour/minute token and request statistics, a 26-week activity heatmap, cache-hit-rate curve, per-model donut and list, and a settings page; it appends its cost item after the official session bottom bar (per-turn cost chips included, no separate detail button), renders the official cache-hit-rate number with two decimals, and estimates costs from multi-condition, time-segmented pricing rules. Re-implemented from HaoyueQin/dsh-usage-statistics-panel with extensions.

SiYuan (思源笔记) notes integration: 17 siyuan_* host tools covering notebook and document listing, full-text search, SQL query, reading documents and blocks, creating and appending content, moving and renaming documents, daily notes and block attributes, plus a Web settings page for the SiYuan URL, API token and per-tool switches.

Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.